hadoop 用MR实现join操作

a.txt
id    name 
001   iphone6
002   xiaominote
003   mate7
004   nubia
005   meilan

b.txt

id    orderid  
001     00101
001     00110
002     01001
...

001   iphone6-->a  00101-->b  00110-->b



select a.name,b.orderid from a,b where a.id=b.id
iphone6  00101
iphone6  00110

package com.test.hadoop.mr.JoinQuery;

import java.io.IOException;
import java.util.ArrayList;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class JoinQuery {

	public static class JoinQueryMapper extends Mapper<LongWritable, Text, Text, Text> {
		private Text k = new Text();
		private Text v = new Text();

		@Override
		protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
				throws IOException, InterruptedException {
			String record = value.toString();
			String[] fields = StringUtils.split(record, "\t");
			String id = fields[0];
			String name = fields[1];

			FileSplit inputSplit = (FileSplit) context.getInputSplit();
			String fileName = inputSplit.getPath().getName();

			k.set(id);
			v.set(name + "-->" + fileName);

			// k:001 v:ipone6->a.txt
			context.write(k, v);
		}
	}

	public static class JoinQueryReducer extends Reducer<Text, Text, Text, Text> {
		// k:001 values: [iphone6-->a.txt, 00101-->b.txt,00110-->b.txt]
		@Override
		protected void reduce(Text key, Iterable<Text> values, Context context)
				throws IOException, InterruptedException {
			// 第一次循环拿出a表中的那个字段
			String lefKey = "";
			ArrayList<String> rightFields = new ArrayList<>();
			for (Text value : values) {
				if (value.toString().contains("a.txt")) {
					lefKey = StringUtils.split(value.toString(), "-->")[0];
				} else {
					rightFields.add(value.toString());
				}
			}

			// 再用leftkey去遍历拼接b表中的字段，并输出结果
			for (String field : rightFields) {
				String result = "";
				result += lefKey + "\t" + StringUtils.split(field.toString(), "-->")[0];
				context.write(new Text(lefKey), new Text(result));
			}

		}
	}

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		Configuration conf = new Configuration();
		Job joinJob = Job.getInstance(conf);

		joinJob.setJarByClass(JoinQuery.class);

		joinJob.setMapperClass(JoinQueryMapper.class);
		joinJob.setReducerClass(JoinQueryReducer.class);

		joinJob.setOutputKeyClass(Text.class);
		joinJob.setOutputValueClass(Text.class);

		FileInputFormat.setInputPaths(joinJob, new Path("D:/BaiduYunDownload/hadoopjoin/srcData"));
		FileOutputFormat.setOutputPath(joinJob, new Path("D:/BaiduYunDownload/hadoopjoin/out"));

		joinJob.waitForCompletion(true);
	}
}